Serveur MCP
Agent Reliability
dev.agentreliability/agent-reliability
Ce que fait ce MCP
Searches and analyzes a sourced knowledge corpus about testing, benchmarking, auditing, and reliability methods for autonomous AI agents.
Capacités
Outils
9
outils
answer
Answer a question about Agent Reliability
Answer a question from the corpus, or refuse. Returns only the claims that bear on the question, each with the sources it cites and its editorial confidence. When the corpus cannot answer, answered is false and abstention_reason plus missing_topics say what was not covered â a refusal is a real result here, not an error. Use this when the user asked a question in words; use search when you want to see the candidates yourself.
Lecture seule
Idempotent
Schéma d’entrée
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['question'], 'properties': {'question': {'type': 'string', 'maxLength': 300, 'minLength': 3, 'description': 'The question to answer, in the words the user asked it.'}}}
Schéma de sortie
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['answered', 'match_threshold', 'missing_topics', 'candidates'], 'properties': {'claims': {'type': 'array', 'items': {'type': 'object', 'required': ['text', 'confidence', 'sources', 'relevance'], 'properties': {'text': {'type': 'string'}, 'sources': {'type': 'array', 'items': {'type': 'object', 'required': ['id', 'title'], 'properties': {'id': {'type': 'string'}, 'url': {'type': 'string'}, 'title': {'type': 'string'}}, 'additionalProperties': False}}, 'relevance': {'type': 'number'}, 'confidence': {'type': 'number'}}, 'additionalProperties': False}}, 'entity': {'type': 'object', 'required': ['id', 'type', 'name', 'summary', 'tags', 'evidence_tier', 'confidence', 'last_verified', 'canonical_url', 'api_url'], 'properties': {'x': {'type': 'object', 'description': 'Indexed instance-specific attributes, grouped by namespace â\x80\x94 the same fields api/index.json publishes. Absent when the instance declares none.', 'propertyNames': {'type': 'string'}, 'additionalProperties': {'type': 'object', 'propertyNames': {'type': 'string'}, 'additionalProperties': {}}}, 'id': {'type': 'string'}, 'name': {'type': 'string'}, 'tags': {'type': 'array', 'items': {'type': 'string'}}, 'type': {'type': 'string'}, 'api_url': {'type': 'string'}, 'summary': {'type': 'string'}, 'confidence': {'type': 'number'}, 'canonical_url': {'type': 'string'}, 'evidence_tier': {'type': 'string'}, 'last_verified': {'type': 'string'}}, 'additionalProperties': False}, 'margin': {'type': 'number', 'description': 'Relative gap between the best candidate and the runner-up. A small margin means the corpus cannot tell them apart.'}, 'answered': {'type': 'boolean'}, 'coverage': {'type': 'number', 'description': "Share of the question's information the winning object accounts for, weighted by term rarity."}, 'candidates': {'type': 'array', 'items': {'type': 'object', 'required': ['id', 'score', 'coverage'], 'properties': {'id': {'type': 'string'}, 'score': {'type': 'number'}, 'coverage': {'type': 'number'}}, 'additionalProperties': False}, 'description': 'Near misses, so a refusal is still a lead. Present whether or not the question was answered.'}, 'match_score': {'type': 'number'}, 'matched_fields': {'type': 'array', 'items': {'type': 'string'}}, 'missing_topics': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Meaningful words in the question that appear nowhere in the winning object â\x80\x94 the gap, named.'}, 'match_threshold': {'type': 'number', 'description': 'The coverage this corpus requires before it will answer at all.'}, 'match_confidence': {'type': 'number', 'description': "How well the answer fits the QUESTION â\x80\x94 retrieval confidence, not editorial. Never confuse it with a claim's own confidence, which is how much the corpus stands behind the statement."}, 'matched_question': {'type': 'string', 'description': 'The stored question this was matched to, when the answer came from one.'}, 'abstention_reason': {'type': 'string', 'description': 'Why the corpus declined: empty_query, no_candidates, below_coverage, ambiguous_candidates or no_intent_match.'}}, 'additionalProperties': False}
compare
Compare Agent Reliability objects side by side
Two to six knowledge objects side by side: their cards, every indexed attribute as a matrix (the same fields api/index.json publishes, null where an object does not say), the tags they share, the relations that run between them, the neighbours they have in common, and each one's claims with sources and confidence. Use this when the question is 'X vs Y', 'is X the same as Y' or 'how does X differ from Y' â search or get_topic first if you only have names, then pass the ids. An unknown id lands in `missing` with a near-miss suggestion and the rest are still compared.
Lecture seule
Idempotent
Schéma d’entrée
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['ids'], 'properties': {'ids': {'type': 'array', 'items': {'type': 'string', 'maxLength': 100, 'minLength': 1}, 'maxItems': 6, 'minItems': 2, 'description': 'Two to six knowledge object ids, as returned by search, get_topic or get_related, in the order you want the columns.'}}}
Schéma de sortie
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['found', 'missing', 'objects', 'facets', 'shared_tags', 'relations_between', 'shared_neighbours', 'claims'], 'properties': {'found': {'type': 'boolean', 'description': 'True only when every id resolved.'}, 'claims': {'type': 'object', 'description': "Every compared object's claims, keyed by object id.", 'propertyNames': {'type': 'string'}, 'additionalProperties': {'type': 'array', 'items': {'type': 'object', 'required': ['text', 'confidence', 'sources'], 'properties': {'text': {'type': 'string'}, 'sources': {'type': 'array', 'items': {'type': 'object', 'required': ['id', 'title'], 'properties': {'id': {'type': 'string'}, 'url': {'type': 'string'}, 'title': {'type': 'string'}}, 'additionalProperties': False}}, 'confidence': {'type': 'number'}}, 'additionalProperties': False}}}, 'facets': {'type': 'array', 'items': {'type': 'object', 'required': ['field', 'values'], 'properties': {'field': {'type': 'string', 'description': 'namespace.field, as declared in the instance blueprint'}, 'values': {'type': 'object', 'description': 'Value per object id; null where that object does not carry the field.', 'propertyNames': {'type': 'string'}, 'additionalProperties': {}}}, 'additionalProperties': False}}, 'missing': {'type': 'array', 'items': {'type': 'string'}, 'description': 'The ids that resolved to nothing, in the order asked.'}, 'objects': {'type': 'array', 'items': {'type': 'object', 'required': ['id', 'type', 'name', 'summary', 'tags', 'evidence_tier', 'confidence', 'last_verified', 'canonical_url', 'api_url'], 'properties': {'x': {'type': 'object', 'description': 'Indexed instance-specific attributes, grouped by namespace â\x80\x94 the same fields api/index.json publishes. Absent when the instance declares none.', 'propertyNames': {'type': 'string'}, 'additionalProperties': {'type': 'object', 'propertyNames': {'type': 'string'}, 'additionalProperties': {}}}, 'id': {'type': 'string'}, 'name': {'type': 'string'}, 'tags': {'type': 'array', 'items': {'type': 'string'}}, 'type': {'type': 'string'}, 'api_url': {'type': 'string'}, 'summary': {'type': 'string'}, 'confidence': {'type': 'number'}, 'canonical_url': {'type': 'string'}, 'evidence_tier': {'type': 'string'}, 'last_verified': {'type': 'string'}}, 'additionalProperties': False}}, 'recovery': {'type': 'object', 'required': ['available_count', 'available', 'next_tool', 'hint'], 'properties': {'hint': {'type': 'string'}, 'available': {'type': 'array', 'items': {'type': 'string'}}, 'next_tool': {'type': 'string'}, 'did_you_mean': {'type': 'array', 'items': {'type': 'string'}}, 'available_count': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991}, 'available_truncated': {'type': 'boolean'}}, 'additionalProperties': False}, 'shared_tags': {'type': 'array', 'items': {'type': 'string'}}, 'relations_between': {'type': 'array', 'items': {'type': 'object', 'required': ['from', 'rel', 'to'], 'properties': {'to': {'type': 'string'}, 'rel': {'type': 'string'}, 'from': {'type': 'string'}}, 'additionalProperties': False}}, 'shared_neighbours': {'type': 'array', 'items': {'type': 'object', 'required': ['id', 'name', 'canonical_url', 'via'], 'properties': {'id': {'type': 'string'}, 'via': {'type': 'array', 'items': {'type': 'object', 'required': ['from', 'rel'], 'properties': {'rel': {'type': 'string'}, 'from': {'type': 'string'}}, 'additionalProperties': False}}, 'name': {'type': 'string'}, 'canonical_url': {'type': 'string'}}, 'additionalProperties': False}}}, 'additionalProperties': False}
get_entity
Get one Agent Reliability knowledge object
Fetch one knowledge object by id, with its claims and the sources each claim cites. Use this once search, answer or get_topic has given you an id. An unknown id is not a dead end: the answer names near-miss ids you can retry with.
Lecture seule
Idempotent
Schéma d’entrée
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['id'], 'properties': {'id': {'type': 'string', 'maxLength': 100, 'minLength': 1, 'description': "The knowledge object's id, as returned by search, answer, get_topic or get_related â\x80\x94 the last segment of its canonical URL."}}}
Schéma de sortie
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['found'], 'properties': {'found': {'type': 'boolean'}, 'entity': {'type': 'object', 'required': ['id', 'type', 'name', 'summary', 'tags', 'evidence_tier', 'confidence', 'last_verified', 'canonical_url', 'api_url', 'questions', 'claims', 'media'], 'properties': {'x': {'type': 'object', 'description': 'Indexed instance-specific attributes, grouped by namespace â\x80\x94 the same fields api/index.json publishes. Absent when the instance declares none.', 'propertyNames': {'type': 'string'}, 'additionalProperties': {'type': 'object', 'propertyNames': {'type': 'string'}, 'additionalProperties': {}}}, 'id': {'type': 'string'}, 'body': {'type': 'string'}, 'name': {'type': 'string'}, 'tags': {'type': 'array', 'items': {'type': 'string'}}, 'type': {'type': 'string'}, 'media': {'type': 'array', 'items': {'type': 'object', 'required': ['id', 'url', 'alt', 'credit', 'license_spdx', 'permissions'], 'properties': {'id': {'type': 'string'}, 'alt': {'type': 'string'}, 'url': {'type': 'string'}, 'width': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991}, 'credit': {'type': 'string'}, 'height': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991}, 'caption': {'type': 'string'}, 'supports': {'type': 'string'}, 'permissions': {'type': 'object', 'propertyNames': {'type': 'string'}, 'additionalProperties': {'type': 'boolean'}}, 'license_spdx': {'type': 'string'}}, 'additionalProperties': False}}, 'claims': {'type': 'array', 'items': {'type': 'object', 'required': ['text', 'confidence', 'sources'], 'properties': {'text': {'type': 'string'}, 'sources': {'type': 'array', 'items': {'type': 'object', 'required': ['id', 'title'], 'properties': {'id': {'type': 'string'}, 'url': {'type': 'string'}, 'title': {'type': 'string'}}, 'additionalProperties': False}}, 'confidence': {'type': 'number'}}, 'additionalProperties': False}}, 'api_url': {'type': 'string'}, 'summary': {'type': 'string'}, 'questions': {'type': 'array', 'items': {'type': 'string'}}, 'confidence': {'type': 'number'}, 'canonical_url': {'type': 'string'}, 'evidence_tier': {'type': 'string'}, 'last_verified': {'type': 'string'}}, 'additionalProperties': False}, 'recovery': {'type': 'object', 'required': ['available_count', 'available', 'next_tool', 'hint'], 'properties': {'hint': {'type': 'string'}, 'available': {'type': 'array', 'items': {'type': 'string'}}, 'next_tool': {'type': 'string'}, 'did_you_mean': {'type': 'array', 'items': {'type': 'string'}}, 'available_count': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991}, 'available_truncated': {'type': 'boolean'}}, 'additionalProperties': False}}, 'additionalProperties': False}
get_latest
Latest verified Agent Reliability objects
Most recently verified knowledge objects (freshness signal). Use this to judge how current the corpus is, or to see what changed since you last read it. It ranks by verification date and ignores your topic entirely â use search or get_topic when you want objects that are relevant rather than recent.
Lecture seule
Idempotent
Schéma d’entrée
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'properties': {'limit': {'type': 'integer', 'default': 10, 'maximum': 25, 'minimum': 1, 'description': 'How many recently verified objects to return, newest verification first.'}}}
Schéma de sortie
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['results', 'total'], 'properties': {'total': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991}, 'results': {'type': 'array', 'items': {'type': 'object', 'required': ['id', 'type', 'name', 'summary', 'tags', 'evidence_tier', 'confidence', 'last_verified', 'canonical_url', 'api_url'], 'properties': {'x': {'type': 'object', 'description': 'Indexed instance-specific attributes, grouped by namespace â\x80\x94 the same fields api/index.json publishes. Absent when the instance declares none.', 'propertyNames': {'type': 'string'}, 'additionalProperties': {'type': 'object', 'propertyNames': {'type': 'string'}, 'additionalProperties': {}}}, 'id': {'type': 'string'}, 'name': {'type': 'string'}, 'tags': {'type': 'array', 'items': {'type': 'string'}}, 'type': {'type': 'string'}, 'api_url': {'type': 'string'}, 'summary': {'type': 'string'}, 'confidence': {'type': 'number'}, 'canonical_url': {'type': 'string'}, 'evidence_tier': {'type': 'string'}, 'last_verified': {'type': 'string'}}, 'additionalProperties': False}}}, 'additionalProperties': False}
get_overview
Overview of Agent Reliability
Corpus overview: what this instance knows, counts by type, published tags, freshness. Use this first when you land here and do not yet know whether this corpus can answer your question.
Lecture seule
Idempotent
Schéma d’entrée
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'properties': {}}
Schéma de sortie
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['instance', 'description', 'total_objects', 'by_type', 'tags', 'newest_verification', 'oldest_verification', 'total_media'], 'properties': {'tags': {'type': 'array', 'items': {'type': 'string'}}, 'by_type': {'type': 'object', 'propertyNames': {'type': 'string'}, 'additionalProperties': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991}}, 'instance': {'type': 'string'}, 'description': {'type': 'string'}, 'total_media': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991}, 'total_objects': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991}, 'newest_verification': {'type': 'string'}, 'oldest_verification': {'type': 'string'}}, 'additionalProperties': False}
get_related
Traverse the Agent Reliability knowledge graph
Graph neighbours of an object: outgoing and incoming relations, each with its relation type. PAGED: 25 relations by default, 200 at most, and a response budget of about 64 KB per call â a page over budget comes back shorter WITH a next_cursor, never truncated. One cursor walks both directions, outgoing first; its absence means you have the last page. Use this after get_entity to widen an answer with adjacent objects. It walks one hop from an id you already have â use search when you have a question and no starting object.
Lecture seule
Idempotent
Schéma d’entrée
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['id'], 'properties': {'id': {'type': 'string', 'maxLength': 100, 'minLength': 1, 'description': 'The knowledge object to walk out from, by id.'}, 'limit': {'type': 'integer', 'maximum': 200, 'minimum': 1, 'description': 'How many relations to return, across both directions. Defaults to 25.'}, 'cursor': {'type': 'string', 'maxLength': 200, 'minLength': 1, 'description': 'Continue from a previous call: pass the next_cursor it returned. Opaque; do not construct one.'}}}
Schéma de sortie
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['found'], 'properties': {'found': {'type': 'boolean'}, 'total': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': 'How many relations this object has in both directions, before paging.'}, 'incoming': {'type': 'array', 'items': {'type': 'object', 'required': ['rel', 'entity'], 'properties': {'rel': {'type': 'string'}, 'entity': {'type': 'object', 'required': ['id', 'type', 'name', 'summary', 'tags', 'evidence_tier', 'confidence', 'last_verified', 'canonical_url', 'api_url'], 'properties': {'x': {'type': 'object', 'description': 'Indexed instance-specific attributes, grouped by namespace â\x80\x94 the same fields api/index.json publishes. Absent when the instance declares none.', 'propertyNames': {'type': 'string'}, 'additionalProperties': {'type': 'object', 'propertyNames': {'type': 'string'}, 'additionalProperties': {}}}, 'id': {'type': 'string'}, 'name': {'type': 'string'}, 'tags': {'type': 'array', 'items': {'type': 'string'}}, 'type': {'type': 'string'}, 'api_url': {'type': 'string'}, 'summary': {'type': 'string'}, 'confidence': {'type': 'number'}, 'canonical_url': {'type': 'string'}, 'evidence_tier': {'type': 'string'}, 'last_verified': {'type': 'string'}}, 'additionalProperties': False}}, 'additionalProperties': False}}, 'outgoing': {'type': 'array', 'items': {'type': 'object', 'required': ['rel', 'entity'], 'properties': {'rel': {'type': 'string'}, 'entity': {'type': 'object', 'required': ['id', 'type', 'name', 'summary', 'tags', 'evidence_tier', 'confidence', 'last_verified', 'canonical_url', 'api_url'], 'properties': {'x': {'type': 'object', 'description': 'Indexed instance-specific attributes, grouped by namespace â\x80\x94 the same fields api/index.json publishes. Absent when the instance declares none.', 'propertyNames': {'type': 'string'}, 'additionalProperties': {'type': 'object', 'propertyNames': {'type': 'string'}, 'additionalProperties': {}}}, 'id': {'type': 'string'}, 'name': {'type': 'string'}, 'tags': {'type': 'array', 'items': {'type': 'string'}}, 'type': {'type': 'string'}, 'api_url': {'type': 'string'}, 'summary': {'type': 'string'}, 'confidence': {'type': 'number'}, 'canonical_url': {'type': 'string'}, 'evidence_tier': {'type': 'string'}, 'last_verified': {'type': 'string'}}, 'additionalProperties': False}}, 'additionalProperties': False}}, 'recovery': {'type': 'object', 'required': ['available_count', 'available', 'next_tool', 'hint'], 'properties': {'hint': {'type': 'string'}, 'available': {'type': 'array', 'items': {'type': 'string'}}, 'next_tool': {'type': 'string'}, 'did_you_mean': {'type': 'array', 'items': {'type': 'string'}}, 'available_count': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991}, 'available_truncated': {'type': 'boolean'}}, 'additionalProperties': False}, 'returned': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991}, 'next_cursor': {'type': 'string', 'description': 'Pass to the next call to continue. ABSENT means this was the last page.'}}, 'additionalProperties': False}
get_sources
Sources behind Agent Reliability
The instance's source registry â each entry with its evidence tier, reliability and access date. PAGED: 25 entries by default, 200 at most, and a response budget of about 64 KB per call â a page over budget comes back shorter WITH a next_cursor, never truncated. Read next_cursor and call again to continue; its absence means you have the last page. Filter by object_id, tier, host or accessed_since to avoid paging through a registry you do not need. Use this when you need the registry entry behind a citation, or a sample of the whole registry to judge the corpus before trusting it; get_entity already tells you which sources a claim cites.
Lecture seule
Idempotent
Schéma d’entrée
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'properties': {'host': {'type': 'string', 'maxLength': 120, 'minLength': 1, 'description': 'Only sources whose URL is served by this host, compared without a leading www. A source with no URL never matches.'}, 'tier': {'type': 'string', 'maxLength': 60, 'minLength': 1, 'description': 'Only sources of this evidence tier, spelled exactly as get_sources reports it.'}, 'limit': {'type': 'integer', 'maximum': 200, 'minimum': 1, 'description': 'How many entries to return. Defaults to 25.'}, 'cursor': {'type': 'string', 'maxLength': 200, 'minLength': 1, 'description': 'Continue from a previous call: pass the next_cursor it returned. Opaque; do not construct one.'}, 'object_id': {'type': 'string', 'maxLength': 100, 'minLength': 1, 'description': 'Restrict the answer to the sources cited by this knowledge object. Omit it to page the whole registry.'}, 'accessed_since': {'type': 'string', 'maxLength': 10, 'minLength': 4, 'description': 'Only sources accessed on or after this ISO date (YYYY-MM-DD).'}}}
Schéma de sortie
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['found', 'sources', 'total', 'returned'], 'properties': {'found': {'type': 'boolean'}, 'total': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': 'How many sources matched the filters, before paging.'}, 'sources': {'type': 'array', 'items': {'type': 'object', 'required': ['id', 'title', 'tier', 'reliability', 'accessed'], 'properties': {'id': {'type': 'string'}, 'url': {'type': 'string'}, 'tier': {'type': 'string'}, 'title': {'type': 'string'}, 'accessed': {'type': 'string'}, 'reliability': {'type': 'number'}}, 'additionalProperties': False}}, 'recovery': {'type': 'object', 'required': ['available_count', 'available', 'next_tool', 'hint'], 'properties': {'hint': {'type': 'string'}, 'available': {'type': 'array', 'items': {'type': 'string'}}, 'next_tool': {'type': 'string'}, 'did_you_mean': {'type': 'array', 'items': {'type': 'string'}}, 'available_count': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991}, 'available_truncated': {'type': 'boolean'}}, 'additionalProperties': False}, 'returned': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991}, 'next_cursor': {'type': 'string', 'description': 'Pass to the next call to continue. ABSENT means this was the last page.'}}, 'additionalProperties': False}
get_topic
Browse Agent Reliability by topic
List the knowledge objects carrying a tag (topics are content-backed tags). PAGED: 25 objects by default, 200 at most, and a response budget of about 64 KB per call â a page over budget comes back shorter WITH a next_cursor, never truncated. Read next_cursor and call again to continue, and its absence means you have the last page. Use this to browse a known topic; use search when you have a question rather than a tag, and get_overview to see which tags exist. An unknown tag comes back with the topics that do exist, so a miss still moves you forward.
Lecture seule
Idempotent
Schéma d’entrée
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['tag'], 'properties': {'tag': {'type': 'string', 'maxLength': 100, 'minLength': 1, 'description': 'The topic to list, spelled exactly as get_overview publishes it. Every published topic has objects under it, so an empty answer means the topic does not exist.'}, 'limit': {'type': 'integer', 'maximum': 200, 'minimum': 1, 'description': 'How many objects to return. Defaults to 25.'}, 'cursor': {'type': 'string', 'maxLength': 200, 'minLength': 1, 'description': 'Continue from a previous call: pass the next_cursor it returned. Opaque; do not construct one.'}}}
Schéma de sortie
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['tag', 'results', 'total', 'returned'], 'properties': {'tag': {'type': 'string'}, 'total': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': 'How many objects carry this tag, before paging.'}, 'results': {'type': 'array', 'items': {'type': 'object', 'required': ['id', 'type', 'name', 'summary', 'tags', 'evidence_tier', 'confidence', 'last_verified', 'canonical_url', 'api_url'], 'properties': {'x': {'type': 'object', 'description': 'Indexed instance-specific attributes, grouped by namespace â\x80\x94 the same fields api/index.json publishes. Absent when the instance declares none.', 'propertyNames': {'type': 'string'}, 'additionalProperties': {'type': 'object', 'propertyNames': {'type': 'string'}, 'additionalProperties': {}}}, 'id': {'type': 'string'}, 'name': {'type': 'string'}, 'tags': {'type': 'array', 'items': {'type': 'string'}}, 'type': {'type': 'string'}, 'api_url': {'type': 'string'}, 'summary': {'type': 'string'}, 'confidence': {'type': 'number'}, 'canonical_url': {'type': 'string'}, 'evidence_tier': {'type': 'string'}, 'last_verified': {'type': 'string'}}, 'additionalProperties': False}}, 'recovery': {'type': 'object', 'required': ['available_count', 'available', 'next_tool', 'hint'], 'properties': {'hint': {'type': 'string'}, 'available': {'type': 'array', 'items': {'type': 'string'}}, 'next_tool': {'type': 'string'}, 'did_you_mean': {'type': 'array', 'items': {'type': 'string'}}, 'available_count': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991}, 'available_truncated': {'type': 'boolean'}}, 'additionalProperties': False}, 'returned': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991}, 'next_cursor': {'type': 'string', 'description': 'Pass to the next call to continue. ABSENT means this was the last page.'}}, 'additionalProperties': False}
search
Search Agent Reliability
Full-text search over the knowledge graph. Matching ignores accents and apostrophes, so query in the user's own words; every hit carries the fields it matched and a score. BM25 relevance: each query term is weighted by how RARE it is in this corpus and by where it hits (name 3, tags 2, questions 2, body 1). A hit must also cover a minimum share of the question's information, measured in the same rarity weights â matching only common words does not qualify. Centrality (how many objects point at this one) breaks TIES ONLY and is never part of the score, so it cannot make an irrelevant object rank. Two hits with the same matched_fields can still differ: the score is rarity-weighted, so matching a rare term is worth more than matching a common one. Use this whenever you have a question rather than an id, then follow up with get_entity.
Lecture seule
Idempotent
Schéma d’entrée
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['query'], 'properties': {'limit': {'type': 'integer', 'default': 10, 'maximum': 25, 'minimum': 1, 'description': 'How many ranked hits to return, best first.'}, 'query': {'type': 'string', 'maxLength': 200, 'minLength': 1, 'description': "What to look for, in the user's own words. Matched against titles, questions, claim text and tags; accents and apostrophes are ignored, so 'jose' finds 'José'."}}}
Schéma de sortie
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['results', 'total'], 'properties': {'total': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991}, 'results': {'type': 'array', 'items': {'type': 'object', 'required': ['id', 'type', 'name', 'summary', 'tags', 'evidence_tier', 'confidence', 'last_verified', 'canonical_url', 'api_url', 'score', 'matched_fields', 'coverage'], 'properties': {'x': {'type': 'object', 'description': 'Indexed instance-specific attributes, grouped by namespace â\x80\x94 the same fields api/index.json publishes. Absent when the instance declares none.', 'propertyNames': {'type': 'string'}, 'additionalProperties': {'type': 'object', 'propertyNames': {'type': 'string'}, 'additionalProperties': {}}}, 'id': {'type': 'string'}, 'name': {'type': 'string'}, 'tags': {'type': 'array', 'items': {'type': 'string'}}, 'type': {'type': 'string'}, 'score': {'type': 'number', 'description': "BM25 relevance: each query term is weighted by how RARE it is in this corpus and by where it hits (name 3, tags 2, questions 2, body 1). A hit must also cover a minimum share of the question's information, measured in the same rarity weights â\x80\x94 matching only common words does not qualify. Centrality (how many objects point at this one) breaks TIES ONLY and is never part of the score, so it cannot make an irrelevant object rank. Two hits with the same matched_fields can still differ: the score is rarity-weighted, so matching a rare term is worth more than matching a common one."}, 'api_url': {'type': 'string'}, 'summary': {'type': 'string'}, 'coverage': {'type': 'number', 'description': "Share of the question's information this object accounts for, weighted by term rarity. 1 means every meaningful word in the query is present; a low value with a high score means the object matched common words only."}, 'confidence': {'type': 'number'}, 'canonical_url': {'type': 'string'}, 'evidence_tier': {'type': 'string'}, 'last_verified': {'type': 'string'}, 'matched_fields': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Which fields the query hit: name, tags, questions, summary, claims. Does NOT determine the score on its own.'}}, 'additionalProperties': False}}}, 'additionalProperties': False}
Historique
Modifications récentes des outils
Ajouté
compare
17 September 2026 12:39
Ajouté
get_overview
17 September 2026 12:39
Ajouté
get_latest
17 September 2026 12:39
Ajouté
get_related
17 September 2026 12:39
Ajouté
get_sources
17 September 2026 12:39
Ajouté
answer
17 September 2026 12:39
Ajouté
get_topic
17 September 2026 12:39
Ajouté
get_entity
17 September 2026 12:39
Ajouté
search
17 September 2026 12:39
Découvrir
Serveurs MCP similaires
x711 — Universal Agent Gas Station
io.github.0580iris-lang/x711-gas-station
Provides agents with web observation and interaction, search and retrieval, sandboxed computation, inter-agent communication, col…
There's An AI For That
com.theresanaiforthat/taaft
Searches and retrieves public information about AI tools, models, companies, MCP servers, devices, events, investors, papers, rep…
TensorFeed
ai.tensorfeed/mcp-server
Provides AI industry news, model pricing, service status information, and premium machine-readable tools.
ExMachina AI — agent research rooms
io.github.SecondStageTurbine/exmachina-ai
Provides collaborative research rooms for biomedical findings, source citations, reviews, agent coordination, and reputation trac…
MarketAIVerse
com.marketaiverse/marketaiverse
Catalogs and benchmarks AI models and tools, estimates hardware compatibility and performance, runs a small model, and supports a…
Hlido Agent Reviews
eu.hlido/mcp
Evaluates AI agents through trust scorecards, behavioral evidence, incident records, capability claims, MCP safety scans, and rec…
aio
org.aioq/aio
Provides AI integrity standards, EU AI Act-aligned evaluations, model benchmark submissions, certification records, RFCs, and AI …
Official OpenAI Announcements & Model Releases — buy per-query in-session (openaiwatch)
com.a2awire/data-openai-announcement-model-release-news
Provides current official OpenAI announcements, model releases, and product news.